Automatic Sentiment Analysis of Citizen Comments: The Case of the Albania Earthquake
GeoHazards · 27.05.2026 · 7 (2) · 62
DOI: 10.3390/geohazards7020062 ↗Kurz gefasst
Fachartikel in der Zeitschrift GeoHazards, online erschienen am 27.05.2026. Verfasst von Diana Contreras und 10 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Engineering and Physical Sciences Research Council, Cardiff University.
Abstract (Originalsprache)
Collecting and analysing data after an earthquake is essential to determine its impact. In 2014, the European Mediterranean Seismological Centre launched the LastQuake system. Its app collects reports on the intensity users feel, along with comments that provide situational awareness. However, text data collected through crowdsourcing platforms is unstructured. Therefore, natural language processing techniques such as sentiment analysis and aspect-based sentiment analysis are necessary to extract meaningful information. On the 26 November 2019, following an earthquake in Albania, the LastQuake app recorded 28,220 reports with user comments. For the current analysis, we sampled comments posted on the exact day of the earthquake, in Albanian: 1678 comments (6%). The most frequent polarity detected in comments from LastQuake app users was negative (52%), followed by positive and neutral. However, manual classification is time-consuming and not feasible during the emergency phase. Therefore, we tested the accuracy of two automatic classification models for sentiment analysis: ‘troberta’ and ‘txlm’. These models were fine-tuned using already-classified text data from the 2020 Aegean earthquake. Using the manual classification as the reference to evaluate the accuracy of the automatic classification models for sentiment analysis yields accuracies of 71% for the ‘troberta’ model and 56% for the ‘txlm’ model.
Förderung
- Engineering and Physical Sciences Research Council
- Cardiff University
Zitieren
APA
Contreras, D., Veliu, E., Antypas, D., Hervas, J., Landès, M., Fallou, L., Koxhaj, D., Bossu, R., Wilkinson, S., Camacho-Collados, J., & Dushi, E. (2026). Automatic Sentiment Analysis of Citizen Comments: The Case of the Albania Earthquake. GeoHazards, 7(2), 62. https://doi.org/10.3390/geohazards7020062
Vancouver
Contreras D, Veliu E, Antypas D, Hervas J, Landès M, Fallou L, et al. Automatic Sentiment Analysis of Citizen Comments: The Case of the Albania Earthquake. GeoHazards. 2026;7(2):62. doi:10.3390/geohazards7020062
BibTeX
@article{Contreras2026,
author = {Contreras, Diana and Veliu, Enes and Antypas, Dimosthenis and Hervas, Javier and Landès, Matthieu and Fallou, Laure and Koxhaj, Damiano and Bossu, Rémy and Wilkinson, Sean and Camacho-Collados, Jose and Dushi, Edmond},
title = {Automatic Sentiment Analysis of Citizen Comments: The Case of the Albania Earthquake},
journal = {GeoHazards},
year = {2026},
volume = {7},
number = {2},
pages = {62},
doi = {10.3390/geohazards7020062}
}
EUVIMED